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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     runoff
    -0.07
    因
    -0.07
    243
    -0.07
     Lose
    -0.07
     Norman
    -0.07
     responses
    -0.07
     AUDIO
    -0.07
    Seattle
    -0.06
     blasts
    -0.06
    south
    -0.06
    POSITIVE LOGITS
    (Action
    0.06
     Fot
    0.06
    peon
    0.06
    HZ
    0.05
    .intro
    0.05
    (enc
    0.05
     cann
    0.05
    masından
    0.05
    вет
    0.05
     seç
    0.05
    Act Density 0.120%

    No Known Activations