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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     infertility
    -0.07
    泊
    -0.07
     ]).
    -0.07
    实际
    -0.07
    Fil
    -0.07
     objects
    -0.06
    　　　　　　　　　　
    -0.06
    ekim
    -0.06
     clinging
    -0.06
     predictors
    -0.06
    POSITIVE LOGITS
    Combo
    0.06
     Ignore
    0.06
    truth
    0.06
    Titulo
    0.06
    well
    0.06
    /msg
    0.06
    avor
    0.06
     Brut
    0.06
     hashlib
    0.06
    ць
    0.05
    Act Density 0.009%

    No Known Activations