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

    Neuronpedia

    INDEX
    Explanations

    call for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cunning
    -0.07
    .userName
    -0.07
    Sad
    -0.07
    	date
    -0.06
    ło
    -0.06
    Climate
    -0.06
    敢
    -0.06
     sagte
    -0.06
     Specialists
    -0.06
    stk
    -0.06
    POSITIVE LOGITS
     compartir
    0.07
     airplane
    0.07
    돠
    0.07
    뉜
    0.07
    -connect
    0.07
    .Pool
    0.07
     DIM
    0.06
     بص
    0.06
    在北京
    0.06
    .setError
    0.06
    Act Density 0.039%

    No Known Activations