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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     steps
    -0.07
     posted
    -0.06
    iais
    -0.06
    αν
    -0.06
    ds
    -0.06
    .ob
    -0.06
    _y
    -0.06
    Hook
    -0.06
    holes
    -0.06
    .q
    -0.06
    POSITIVE LOGITS
     onemocnění
    0.07
     cadastr
    0.06
    major
    0.06
    ��
    0.06
     DPS
    0.06
    .invoke
    0.06
     arkadaş
    0.06
    .names
    0.06
    0.06
    DM
    0.06
    Act Density 0.043%

    No Known Activations