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

    Neuronpedia

    INDEX
    Explanations

    math and currency

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     derivation
    0.46
     derives
    0.46
     derive
    0.45
    into
    0.44
     Der
    0.43
     derivations
    0.43
     into
    0.42
    Der
    0.42
     ^{
    0.41
     deriva
    0.40
    POSITIVE LOGITS
     resulting
    0.38
     Determining
    0.38
     determining
    0.37
    resulting
    0.36
    ####
    0.35
    とな
    0.35
     Ihrem
    0.35
    േ
    0.34
     परन्तु
    0.33
     Thank
    0.33
    Act Density 0.004%

    No Known Activations