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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marble
    -0.06
    Episode
    -0.06
    =params
    -0.06
     player
    -0.06
     manifests
    -0.06
     convict
    -0.06
    ↵↵↵
    -0.06
     lest
    -0.06
     Fast
    -0.06
     اکتبر
    -0.06
    POSITIVE LOGITS
    _ATOMIC
    0.07
    .Common
    0.07
     lành
    0.06
    IGN
    0.06
     Croatia
    0.06
     ung
    0.06
    enedor
    0.06
    .Dep
    0.06
     olmadığı
    0.06
    pees
    0.06
    Act Density 0.006%

    No Known Activations