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

    Neuronpedia

    INDEX
    Explanations

    combining into something more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ज़्यादा
    0.47
    time
    0.46
    rak
    0.46
    dough
    0.46
    ya
    0.46
    replace
    0.45
    vacuum
    0.45
    decl
    0.44
    ndef
    0.44
    upe
    0.43
    POSITIVE LOGITS
     milij
    0.50
     poise
    0.49
    ？”
    0.49
    ิล
    0.47
     Serv
    0.46
    ？」
    0.46
     monocytes
    0.46
     elu
    0.45
     toplant
    0.44
    Serv
    0.44
    Act Density 0.001%

    No Known Activations