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

    Neuronpedia

    INDEX
    Explanations

    vul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _number
    -0.07
     ghost
    -0.07
    achine
    -0.07
     Isabel
    -0.07
    elocity
    -0.07
    acl
    -0.06
     Chance
    -0.06
     association
    -0.06
    одар
    -0.06
    onenumber
    -0.06
    POSITIVE LOGITS
     vul
    0.15
     Vul
    0.08
    _Variable
    0.07
    <Transform
    0.07
    (pub
    0.06
     stringWith
    0.06
    typ
    0.06
    .ReadFile
    0.06
    که
    0.06
    **,
    0.06
    Act Density 0.001%

    No Known Activations