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

    Neuronpedia

    INDEX
    Explanations

    Crimes and human rights

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _lens
    -0.08
    iya
    -0.07
    โดย
    -0.06
     तहत
    -0.06
    Four
    -0.06
    four
    -0.06
     setInterval
    -0.06
     包
    -0.06
    	div
    -0.06
    broadcast
    -0.06
    POSITIVE LOGITS
    .TextUtils
    0.07
    _likes
    0.07
     paraph
    0.07
    �부
    0.07
     名無しさん
    0.06
    otti
    0.06
    ALLE
    0.06
    ною
    0.06
     Appropri
    0.06
     Cooling
    0.06
    Act Density 0.022%

    No Known Activations