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

    Neuronpedia

    INDEX
    Explanations

    error detection/correction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unc
    -0.07
     energ
    -0.06
    68
    -0.06
    ороз
    -0.06
    nage
    -0.06
    018
    -0.06
    wner
    -0.06
     döndü
    -0.06
    ौ
    -0.06
     Ко
    -0.06
    POSITIVE LOGITS
    .MenuStrip
    0.07
    LIC
    0.07
    .mybatis
    0.06
    SESSION
    0.06
     Missile
    0.06
     knobs
    0.06
     say
    0.06
    –and
    0.06
    opi
    0.06
     missile
    0.06
    Act Density 0.008%

    No Known Activations