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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     대해서
    -0.07
     topLevel
    -0.07
    人気
    -0.06
     Separate
    -0.06
    세
    -0.06
     gw
    -0.06
    改变
    -0.06
    allax
    -0.06
    รษฐ
    -0.05
     뿐
    -0.05
    POSITIVE LOGITS
    ERING
    0.07
    =torch
    0.07
    生的
    0.07
     ****************
    0.07
    usions
    0.07
    ?(
    0.06
    kola
    0.06
    match
    0.06
     Sharp
    0.06
     LETTER
    0.06
    Act Density 0.000%

    No Known Activations