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

    Neuronpedia

    INDEX
    Explanations

    Varied contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    านคร
    -0.07
    ashington
    -0.07
    .area
    -0.06
     виник
    -0.06
     altro
    -0.06
    applicant
    -0.06
     futuristic
    -0.06
     warmly
    -0.06
     Cooke
    -0.06
    裕
    -0.06
    POSITIVE LOGITS
    robat
    0.08
    _process
    0.07
    .attribute
    0.06
    Hillary
    0.06
    holiday
    0.06
    hetics
    0.06
     metast
    0.06
     Gina
    0.06
    451
    0.05
     vez
    0.05
    Act Density 0.001%

    No Known Activations