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

    Neuronpedia

    INDEX
    Explanations

    group

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    astered
    -0.07
     secluded
    -0.07
     رمز
    -0.07
    .UseText
    -0.06
     viêm
    -0.06
    biased
    -0.06
     subjective
    -0.06
    ='
    -0.06
     Sınıf
    -0.06
     đá
    -0.06
    POSITIVE LOGITS
     plurality
    0.07
     μό
    0.07
    "strings
    0.06
    _launcher
    0.06
     excit
    0.06
     Mong
    0.06
    .signup
    0.06
    stan
    0.06
    _SPEC
    0.06
     hardware
    0.06
    Act Density 0.007%

    No Known Activations