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

    Neuronpedia

    INDEX
    Explanations

    calculators and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rat
    0.41
     Oc
    0.40
     Loire
    0.39
     ambiguity
    0.39
    தமிழக
    0.39
     Oaks
    0.38
     oaks
    0.38
     Floret
    0.38
     pecan
    0.37
     cultivators
    0.37
    POSITIVE LOGITS
     নক
    0.44
    ikko
    0.41
     অর্থে
    0.40
    Calle
    0.40
    礦
    0.38
    わざ
    0.37
    ysen
    0.37
    parentNode
    0.36
     preko
    0.36
    ेंडा
    0.36
    Act Density 0.000%

    No Known Activations