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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	center
    -0.07
    _True
    -0.07
     putting
    -0.07
    Height
    -0.07
     magma
    -0.06
    inski
    -0.06
    content
    -0.06
    alte
    -0.06
     lbl
    -0.06
    mention
    -0.06
    POSITIVE LOGITS
    ParticleSystem
    0.06
    月
    0.06
     Steak
    0.06
    _resolve
    0.06
     نقش
    0.06
    noinspection
    0.06
     Transaction
    0.06
     datingsider
    0.06
     songs
    0.06
    気持ち
    0.06
    Act Density 0.021%

    No Known Activations