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

    Neuronpedia

    INDEX
    Explanations

    sausage-like or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     treetops
    0.31
     végétation
    0.31
     xlabel
    0.29
     initialization
    0.29
     rivets
    0.28
     Tabelle
    0.28
     rotates
    0.28
     parametrization
    0.28
     flott
    0.28
     observables
    0.28
    POSITIVE LOGITS
    或
    0.40
    하거나
    0.39
     or
    0.38
     или
    0.36
    または
    0.35
    หรือ
    0.34
    any
    0.34
     또는
    0.33
     અથવા
    0.32
     कोणत्याही
    0.32
    Act Density 2.656%

    No Known Activations