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

    Neuronpedia

    INDEX
    Explanations

    risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -con
    -0.06
    .Store
    -0.06
     я
    -0.06
     vlak
    -0.06
     sẽ
    -0.06
     EINVAL
    -0.06
     metaphor
    -0.06
    пат
    -0.06
    _fil
    -0.06
    _lt
    -0.06
    POSITIVE LOGITS
     pic
    0.06
     complicated
    0.06
     rapidly
    0.06
     somew
    0.06
    ographers
    0.06
    ournament
    0.06
    _memory
    0.06
     questioned
    0.06
    _snapshot
    0.06
     lengths
    0.06
    Act Density 0.007%

    No Known Activations