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

    Neuronpedia

    INDEX
    Explanations

    model responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    simeq
    0.41
    deoxy
    0.41
    ビット
    0.41
     }=
    0.38
     marginLeft
    0.37
    decine
    0.37
     γ
    0.37
     θ
    0.37
     deoxy
    0.37
     systolic
    0.36
    POSITIVE LOGITS
    Link
    0.41
    常量
    0.40
     haven
    0.40
    Sketch
    0.38
    opus
    0.37
    Greg
    0.36
    μαι
    0.36
     link
    0.36
    Main
    0.36
     snippet
    0.36
    Act Density 0.001%

    No Known Activations