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

    Neuronpedia

    INDEX
    Explanations

    programming-related constructs and mathematical expressions

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

    Mathematical or code expressions

    np_acts-logits-general · gemini-2.0-flash

    minus sign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    greif
    -0.52
    UrlEncoded
    -0.50
    uert
    -0.50
    JvmStatic
    -0.49
    hus
    -0.47
     combined
    -0.47
    writeField
    -0.46
    IonicModule
    -0.46
    をかけ
    -0.46
     senso
    -0.45
    POSITIVE LOGITS
     -
    1.24
     −
    1.24
     minus
    1.13
     –
    1.08
     $-$
    1.02
    −
    0.97
     ‐
    0.93
     }-
    0.90
     —
    0.90
    €“
    0.90
    Act Density 0.987%

    No Known Activations