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

    Neuronpedia

    INDEX
    Explanations

    instances of the LaTeX backslash character used for commands

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

    start of user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сылкі
    -0.89
     queſta
    -0.88
     Administrativna
    -0.86
     Monfieur
    -0.84
     autorytatywna
    -0.77
     themſelves
    -0.75
     betweenstory
    -0.75
    adaptiveStyles
    -0.75
     kasarigan
    -0.75
    Tikang
    -0.75
    POSITIVE LOGITS
    .
    0.52
     
    0.46
    ,
    0.45
     program
    0.41
    1
    0.38
    2
    0.36
    T
    0.35
     .
    0.35
    ij
    0.35
    omb
    0.34
    Act Density 0.000%

    No Known Activations