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

    Neuronpedia

    INDEX
    Explanations

    Personal opinions/experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mamak
    -0.07
    -terrorism
    -0.07
     Isl
    -0.06
     lk
    -0.06
    ourced
    -0.06
     premiered
    -0.06
    iped
    -0.06
    _ALIGNMENT
    -0.06
     име
    -0.06
    ueling
    -0.06
    POSITIVE LOGITS
     十
    0.07
     BUILD
    0.06
    (bitmap
    0.06
    xious
    0.06
    τος
    0.06
    ！”
    0.06
     silver
    0.06
    UCH
    0.06
     embodiment
    0.06
    neighbor
    0.06
    Act Density 0.056%

    No Known Activations