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

    Neuronpedia

    INDEX
    Explanations

    Miss followed by names or mismatch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্তা
    0.39
    क्रमण
    0.37
     actief
    0.36
    uent
    0.36
     Rés
    0.36
    チラ
    0.36
    ంప
    0.36
     campa
    0.36
     Opa
    0.36
    騰
    0.36
    POSITIVE LOGITS
    issippi
    0.61
    oula
    0.54
     Muff
    0.54
    ouri
    0.51
    hap
    0.48
    issauga
    0.47
     miss
    0.47
    guided
    0.46
    Apple
    0.46
    brauch
    0.45
    Act Density 0.002%

    No Known Activations