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

    Neuronpedia

    INDEX
    Explanations

    names and specific fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polypes
    0.45
     учеб
    0.42
    劻
    0.41
    ட்சத்திர
    0.41
    ністю
    0.41
    ැන
    0.40
    强者
    0.39
     samano
    0.39
     hémorro
    0.39
    ્ઞ
    0.39
    POSITIVE LOGITS
    en
    0.50
     prover
    0.47
    im
    0.47
    aux
    0.46
    r
    0.46
     Jar
    0.46
     modern
    0.46
    ah
    0.46
    time
    0.45
     rell
    0.45
    Act Density 0.001%

    No Known Activations