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

    Neuronpedia

    INDEX
    Explanations

    grade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     školy
    -0.08
    Johnson
    -0.07
     вп
    -0.07
     Περ
    -0.07
     Norton
    -0.07
     newValue
    -0.06
     scen
    -0.06
     quadratic
    -0.06
     Freeman
    -0.06
    .rb
    -0.06
    POSITIVE LOGITS
    Playlist
    0.07
     disclosing
    0.07
     Certainly
    0.07
     distributes
    0.06
    arnings
    0.06
    YLES
    0.06
    риття
    0.06
    Characters
    0.06
    39
    0.06
    lies
    0.06
    Act Density 0.000%

    No Known Activations