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

    Neuronpedia

    INDEX
    Explanations

    teacher training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bg
    -0.07
     dob
    -0.07
     texte
    -0.06
    -induced
    -0.06
     elif
    -0.06
    bé
    -0.06
    (dataset
    -0.06
     Над
    -0.06
     coroutine
    -0.06
     criar
    -0.06
    POSITIVE LOGITS
     кни
    0.06
     quá
    0.06
     causal
    0.06
    /images
    0.06
     य
    0.06
    参与
    0.06
    .lot
    0.06
    停止
    0.06
     obsess
    0.06
     suffice
    0.06
    Act Density 0.024%

    No Known Activations