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

    Neuronpedia

    INDEX
    Explanations

    Something being moved

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [*
    -0.07
     команди
    -0.06
     слід
    -0.06
    zM
    -0.06
    iate
    -0.06
    [d
    -0.06
    очный
    -0.06
     bitter
    -0.06
     Atari
    -0.05
     Treasurer
    -0.05
    POSITIVE LOGITS
    _DER
    0.07
    .navigationController
    0.07
     eng
    0.07
     Watch
    0.07
    outines
    0.06
    fol
    0.06
    _partner
    0.06
    uş
    0.06
    ruc
    0.06
    oron
    0.06
    Act Density 0.038%

    No Known Activations