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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sebastian
    -0.07
     Kết
    -0.07
    _BACKEND
    -0.06
     kapit
    -0.06
     challenged
    -0.06
     muddy
    -0.06
    Match
    -0.06
    θέ
    -0.06
    структор
    -0.06
     shaded
    -0.06
    POSITIVE LOGITS
    FG
    0.07
    Correction
    0.07
    (abs
    0.06
     abs
    0.06
    aturdays
    0.06
    NEW
    0.06
     Bone
    0.06
     critically
    0.06
     Original
    0.06
    ynom
    0.06
    Act Density 0.008%

    No Known Activations