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

    Neuronpedia

    INDEX
    Explanations

    symbols, locations, family

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    $\
    1.14
    $-$
    1.11
     prospective
    1.06
     repre
    1.03
    戬
    1.03
    Silicon
    1.02
     exposition
    1.01
    行う
    1.01
    Instruction
    1.01
    $(\
    1.00
    POSITIVE LOGITS
    chod
    1.16
     hwnd
    1.14
     hampers
    1.07
    jaman
    1.03
    л
    1.03
     berasal
    1.02
    溏
    1.00
     typh
    0.99
     kayu
    0.99
     clove
    0.97
    Act Density 0.001%

    No Known Activations