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

    Neuronpedia

    INDEX
    Explanations

    bot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anik
    -0.07
    enarios
    -0.07
    InitialState
    -0.06
    Cur
    -0.06
    atos
    -0.06
    ragon
    -0.06
    bi
    -0.06
     pep
    -0.06
    686
    -0.06
     Attached
    -0.06
    POSITIVE LOGITS
    OSH
    0.07
     Pussy
    0.06
     وحدة
    0.06
    (shift
    0.06
    	me
    0.06
     #-}↵↵
    0.06
    ausal
    0.06
     stationed
    0.06
    *y
    0.06
     вис
    0.06
    Act Density 0.005%

    No Known Activations