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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initialization
    -0.07
    -groups
    -0.07
    kh
    -0.07
     Me
    -0.06
     Legislative
    -0.06
    ิท
    -0.06
    skin
    -0.06
     ElseIf
    -0.06
    //-
    -0.06
     "%"
    -0.06
    POSITIVE LOGITS
    řed
    0.07
    (kernel
    0.06
     输
    0.06
    prompt
    0.06
    platz
    0.06
    ře
    0.06
    _verbose
    0.06
     sırada
    0.06
    ست
    0.06
     velk
    0.06
    Act Density 0.004%

    No Known Activations