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

    Neuronpedia

    INDEX
    Explanations

    non-letter characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Johannesburg
    -0.07
    Ey
    -0.06
    效果
    -0.06
    ToDevice
    -0.06
    ']==
    -0.06
     basically
    -0.06
    (us
    -0.06
     contexto
    -0.06
    der
    -0.06
     작업
    -0.05
    POSITIVE LOGITS
     отп
    0.07
     ژ
    0.07
     northeast
    0.07
     WH
    0.07
    ediator
    0.07
    .sg
    0.06
    monthly
    0.06
    yet
    0.06
     revealing
    0.06
     Plays
    0.06
    Act Density 0.010%

    No Known Activations