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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prescription
    -0.07
     Established
    -0.07
     Wildlife
    -0.07
     compares
    -0.07
     смесь
    -0.06
    toupper
    -0.06
    iterate
    -0.06
     contrasts
    -0.06
     суще
    -0.06
    hits
    -0.06
    POSITIVE LOGITS
     MODE
    0.07
     mop
    0.06
     карти
    0.06
    'util
    0.06
     Gab
    0.06
     disk
    0.06
     Sok
    0.06
     vibe
    0.06
     deutsche
    0.06
    	io
    0.06
    Act Density 0.003%

    No Known Activations