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

    Neuronpedia

    INDEX
    Explanations

    saving/keeping records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rotor
    -0.08
    îte
    -0.08
     बदलाव
    -0.08
    Then
    -0.08
    Wildcard
    -0.07
    こんにちは
    -0.07
     freshman
    -0.07
    (Default
    -0.07
    (sizeof
    -0.07
    Influ
    -0.07
    POSITIVE LOGITS
     bewijs
    0.13
     기록
    0.13
     ದಾಖ
    0.12
    记录
    0.12
     preuves
    0.12
     evidence
    0.11
     Evidence
    0.10
     증
    0.10
     evid
    0.10
     хран
    0.10
    Act Density 0.042%

    No Known Activations