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

    Neuronpedia

    INDEX
    Explanations

    say punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rocket
    -0.07
     Veg
    -0.07
    有色金属
    -0.07
    SETTING
    -0.07
    (LayoutInflater
    -0.07
    BOSE
    -0.07
    咥
    -0.07
    执
    -0.07
    -anchor
    -0.07
     energy
    -0.07
    POSITIVE LOGITS
     ili
    0.07
    Overall
    0.07
     Refresh
    0.06
    ,,,
    0.06
    动人
    0.06
     household
    0.06
     Dad
    0.06
     checked
    0.06
    pedia
    0.06
    Try
    0.06
    Act Density 0.002%

    No Known Activations