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

    Neuronpedia

    INDEX
    Explanations

    already done or tried

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     existing
    1.27
    existing
    1.13
    Existing
    1.09
     Existing
    1.09
    既存
    1.04
     EXISTING
    1.01
     existente
    0.98
     existentes
    0.96
    现有
    0.96
     preexisting
    0.96
    POSITIVE LOGITS
    equivalent
    0.40
    agge
    0.38
     Covered
    0.37
    setError
    0.37
    ýt
    0.37
    ikaze
    0.36
    OSH
    0.35
    ValueError
    0.35
    DISABLE
    0.34
    spike
    0.34
    Act Density 0.021%

    No Known Activations