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

    Neuronpedia

    INDEX
    Explanations

    current time markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ным
    1.79
    ע
    1.77
    ר
    1.49
    ן
    1.38
    ку
    1.27
    ع
    1.26
    ளில்
    1.24
    었던
    1.24
     [+]
    1.23
     Helpful
    1.23
    POSITIVE LOGITS
    heres
    1.52
    为止
    1.38
     அடுத்து
    1.38
    estado
    1.37
    ید
    1.25
    væ
    1.25
    og
    1.24
    ise
    1.24
    moves
    1.23
    stantial
    1.22
    Act Density 0.522%

    No Known Activations