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

    Neuronpedia

    INDEX
    Explanations

    Statistical models and truth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Finish
    -0.07
     Help
    -0.07
    好像
    -0.07
    Connect
    -0.07
    因為
    -0.07
    但
    -0.07
     wie
    -0.07
     Do
    -0.07
     forward
    -0.07
    orry
    -0.07
    POSITIVE LOGITS
    teste
    0.07
    izzlies
    0.07
    sätze
    0.07
    ṧ
    0.07
    .toUpperCase
    0.07
    (statearr
    0.07
    PasswordEncoder
    0.06
     ResultSet
    0.06
     Üniversites
    0.06
     arbitrarily
    0.06
    Act Density 0.086%

    No Known Activations