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

    Neuronpedia

    INDEX
    Explanations

    giant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    öğ
    -0.07
     toss
    -0.07
     Fors
    -0.06
    翡翠
    -0.06
     missile
    -0.06
     kolej
    -0.06
    Oper
    -0.06
    getc
    -0.06
    :selected
    -0.06
     bumper
    -0.06
    POSITIVE LOGITS
    𝙧
    0.08
     Validation
    0.07
     standardized
    0.07
     caused
    0.07
     behaviour
    0.07
     khuẩn
    0.07
    Frequency
    0.06
     falta
    0.06
    currentState
    0.06
    Ｙ
    0.06
    Act Density 0.001%

    No Known Activations