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

    Neuronpedia

    INDEX
    Explanations

    academic courses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (E
    -0.08
    Timeout
    -0.07
    ـــ
    -0.07
     eleg
    -0.07
    (Arg
    -0.06
     aux
    -0.06
    _song
    -0.06
     Needle
    -0.06
    _soft
    -0.06
     setPassword
    -0.06
    POSITIVE LOGITS
    Diagnostic
    0.06
     depart
    0.06
     enroll
    0.06
    achinery
    0.06
    さま
    0.06
     Prices
    0.05
    发生
    0.05
    reeNode
    0.05
    运行
    0.05
     wrongful
    0.05
    Act Density 0.001%

    No Known Activations