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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     защ
    -0.07
     mostr
    -0.07
     захисту
    -0.07
    isible
    -0.06
     Mozart
    -0.06
     hazard
    -0.06
    :event
    -0.06
     hashing
    -0.06
    itive
    -0.06
    ění
    -0.06
    POSITIVE LOGITS
    CLIENT
    0.07
    <src
    0.07
     scanning
    0.06
     Unc
    0.06
     hospitalized
    0.06
    oky
    0.06
    serialize
    0.06
    .Meta
    0.06
    ือง
    0.06
     negoci
    0.06
    Act Density 0.000%

    No Known Activations