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

    Neuronpedia

    INDEX
    Explanations

    pert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    puties
    -0.07
    ㄘ
    -0.07
     mentre
    -0.07
    \"");↵
    -0.07
     importantes
    -0.07
     NDP
    -0.07
    ')),↵
    -0.07
    �
    -0.07
     "^
    -0.07
    !),
    -0.07
    POSITIVE LOGITS
     EAR
    0.08
    О
    0.08
    AWN
    0.08
    여
    0.07
     Clinic
    0.07
    OAD
    0.07
    ocal
    0.07
    룬
    0.07
    ская
    0.07
    .Lerp
    0.07
    Act Density 0.003%

    No Known Activations