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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nhựa
    -0.08
     Obtain
    -0.07
    -full
    -0.07
     Binder
    -0.07
     má
    -0.07
    _Man
    -0.07
     Ngài
    -0.07
     inhib
    -0.07
    .Abstractions
    -0.07
    時間が
    -0.07
    POSITIVE LOGITS
     Booth
    0.07
    *angstrom
    0.07
    rent
    0.06
    —it
    0.06
     address
    0.06
    登錄
    0.06
    一段
    0.06
    ショ
    0.06
    其实
    0.06
    .directory
    0.06
    Act Density 0.000%

    No Known Activations