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

    Neuronpedia

    INDEX
    Explanations

    logs and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Suff
    -0.07
     IU
    -0.06
    �
    -0.06
     referencedColumnName
    -0.06
    ipsoid
    -0.06
    _loan
    -0.06
    .matches
    -0.06
    __("
    -0.06
    اء
    -0.06
     tokenizer
    -0.06
    POSITIVE LOGITS
     sistema
    0.08
     teach
    0.07
     música
    0.06
     podob
    0.06
     Kullan
    0.06
     과
    0.06
     진짜
    0.06
     Behaviour
    0.06
     rearr
    0.06
    [from
    0.06
    Act Density 0.224%

    No Known Activations