Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conditional statements and boolean expressions in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "bool" followed by certain tokens

    np_acts-logits-general · gemini-2.0-flash

    boolean values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.48
     Leider
    -0.46
     themſelves
    -0.46
     ſeveral
    -0.44
     intér
    -0.44
    FieldBuilder
    -0.44
     becauſe
    -0.44
     ſche
    -0.44
     expiry
    -0.43
     altrett
    -0.43
    POSITIVE LOGITS
     use
    0.99
     مرئيه
    0.94
    Use
    0.82
     Use
    0.82
     force
    0.82
     need
    0.79
     allow
    0.78
     Force
    0.78
    DockStyle
    0.77
    use
    0.76
    Act Density 0.343%

    No Known Activations