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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    beg
    -0.07
    FK
    -0.07
    η
    -0.06
    ении
    -0.06
    =explode
    -0.06
    _SCALE
    -0.06
    ./
    -0.06
    ize
    -0.06
    �
    -0.06
    .route
    -0.06
    POSITIVE LOGITS
     newUser
    0.07
    、マ
    0.07
     disen
    0.06
    _READONLY
    0.06
    .twitter
    0.06
    /icons
    0.06
     MARK
    0.06
    "default
    0.06
     TRE
    0.06
    "go
    0.06
    Act Density 0.043%

    No Known Activations