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

    Neuronpedia

    INDEX
    Explanations

    I feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    in
    0.60
    leq
    0.52
    tap
    0.51
    Belle
    0.51
    𝙴
    0.51
    tilde
    0.51
    tau
    0.50
    tick
    0.49
    geq
    0.49
    belle
    0.48
    POSITIVE LOGITS
    uch
    0.51
    瞽
    0.50
    нув
    0.49
    ен
    0.48
     Euch
    0.48
    ում
    0.48
    的意思
    0.48
    ಿಂತ
    0.48
     rêves
    0.48
    umā
    0.48
    Act Density 0.004%

    No Known Activations