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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xAB
    -0.07
    .me
    -0.07
     undermining
    -0.07
     Information
    -0.07
    질
    -0.07
    setMessage
    -0.06
    _snapshot
    -0.06
    request
    -0.06
    Ro
    -0.06
    539
    -0.06
    POSITIVE LOGITS
    AST
    0.06
    atched
    0.06
    italize
    0.06
    ітет
    0.06
    (force
    0.06
    альні
    0.06
    .coeff
    0.05
     tended
    0.05
     awaits
    0.05
     Його
    0.05
    Act Density 0.009%

    No Known Activations