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

    Neuronpedia

    INDEX
    Explanations

    James

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    watch
    -0.08
     eat
    -0.07
    硬
    -0.06
    Jac
    -0.06
    �
    -0.06
    .language
    -0.06
     refused
    -0.06
     archives
    -0.06
     architects
    -0.06
    INCLUDE
    -0.06
    POSITIVE LOGITS
     násled
    0.07
     spriteBatch
    0.06
    Intermediate
    0.06
    _http
    0.06
    .;.;.;.;
    0.06
    ssh
    0.06
    \Action
    0.06
     LGPL
    0.06
    _tensors
    0.06
     colle
    0.06
    Act Density 0.002%

    No Known Activations