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

    Neuronpedia

    INDEX
    Explanations

    knock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ego
    -0.69
    eq
    -0.67
    e
    -0.67
    issex
    -0.66
    حياته
    -0.65
    zzleHttp
    -0.64
    unting
    -0.64
    eats
    -0.64
     SDLK
    -0.64
     propOrder
    -0.63
    POSITIVE LOGITS
    setVerticalGroup
    0.77
    iness
    0.53
    back
    0.44
    +:+
    0.44
    nip
    0.40
    igshid
    0.40
    ziná
    0.39
    load
    0.39
    self
    0.38
    harusnya
    0.38
    Act Density 0.057%

    No Known Activations