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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getBoolean
    -0.07
     ak
    -0.07
    -term
    -0.07
    \Middleware
    -0.07
     ”↵↵
    -0.07
    능
    -0.07
     ana
    -0.07
     marijuana
    -0.06
    SqlServer
    -0.06
    敢于
    -0.06
    POSITIVE LOGITS
     Ports
    0.07
     FOLLOW
    0.07
    ♕
    0.07
     SSA
    0.07
    clientes
    0.07
    .ReadFile
    0.06
    (fout
    0.06
    ᵞ
    0.06
    タ
    0.06
     wives
    0.06
    Act Density 0.001%

    No Known Activations