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

    Neuronpedia

    INDEX
    Explanations

    .pdf links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    icoes
    0.40
     Rizzo
    0.37
     Rais
    0.36
     چشم
    0.35
     صن
    0.35
     intangible
    0.35
    ]');
    0.35
    Chancellor
    0.35
    hrt
    0.34
     Paryayvachi
    0.34
    POSITIVE LOGITS
     regrett
    0.43
    exceptions
    0.41
    Exceptions
    0.40
    hadoop
    0.38
     следующих
    0.38
     conferred
    0.37
    elés
    0.37
    BEGIN
    0.36
     precluded
    0.36
    経験
    0.36
    Act Density 0.000%

    No Known Activations