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

    Neuronpedia

    INDEX
    Explanations

    symbols indicating types or structures in programming

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

    user labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URLException
    -0.53
    WM
    -0.49
     edge
    -0.47
     look
    -0.47
     nil
    -0.46
     failure
    -0.45
    SKA
    -0.44
    expandindo
    -0.44
    pot
    -0.44
    hill
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.64
     propOrder
    0.55
    GOTREF
    0.51
     animada
    0.50
    AndEndTag
    0.50
     defaultstate
    0.50
     hendes
    0.50
     femei
    0.46
     abstrait
    0.46
    \{\\
    0.45
    Act Density 0.002%

    No Known Activations