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

    Neuronpedia

    INDEX
    Explanations

    love

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hr
    -0.08
    叫
    -0.06
    ԛ
    -0.06
     Festival
    -0.06
    “(
    -0.06
     kc
    -0.06
    קורא
    -0.06
    难过
    -0.06
     snapped
    -0.06
    三四
    -0.06
    POSITIVE LOGITS
     automotive
    0.08
    特意
    0.08
    broken
    0.07
    abilia
    0.07
     substitution
    0.07
     love
    0.07
    _TIMES
    0.07
     através
    0.07
    .Atomic
    0.07
     satın
    0.07
    Act Density 0.072%

    No Known Activations