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

    Neuronpedia

    INDEX
    Explanations

    freedom of expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рид
    -0.07
    _acl
    -0.07
    LEG
    -0.06
    coat
    -0.06
    ผ
    -0.06
     omp
    -0.06
    ीटर
    -0.06
    ("'
    -0.06
    브
    -0.06
    NavItem
    -0.06
    POSITIVE LOGITS
    .term
    0.07
    _STOP
    0.07
     protagon
    0.06
    remely
    0.06
     Hizmetleri
    0.06
    OOT
    0.06
    Normals
    0.05
     shooting
    0.05
     níž
    0.05
     massacre
    0.05
    Act Density 0.001%

    No Known Activations