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

    Neuronpedia

    INDEX
    Explanations

    «

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ениях
    -0.06
    	str
    -0.06
    EMPL
    -0.06
    ене
    -0.06
    �다
    -0.06
    _r
    -0.06
    'R
    -0.06
    ulen
    -0.06
    _quad
    -0.06
    .phase
    -0.06
    POSITIVE LOGITS
     Kafka
    0.07
     interested
    0.07
     عرب
    0.07
     Dub
    0.07
    ]):↵
    0.07
    ssue
    0.06
     Con
    0.06
     black
    0.06
     Nurse
    0.06
     blir
    0.06
    Act Density 0.001%

    No Known Activations