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

    Neuronpedia

    INDEX
    Explanations

    internal cooling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EM
    0.53
    é
    0.50
    M
    0.49
    G
    0.48
    f
    0.47
    ari
    0.47
    mitz
    0.47
    𝗚
    0.46
    ahh
    0.46
    em
    0.45
    POSITIVE LOGITS
     رائ
    0.51
    انے
    0.48
     koncert
    0.46
    補
    0.46
     bangle
    0.45
     handcuffed
    0.45
     sneakers
    0.44
     hopped
    0.43
     rangle
    0.43
    >,</
    0.43
    Act Density 0.005%

    No Known Activations