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

    Neuronpedia

    INDEX
    Explanations

    advice and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     salts
    0.69
     garam
    0.67
     cisplatin
    0.63
     salt
    0.63
    IfNeeded
    0.63
     Salt
    0.62
     sm
    0.61
     сма
    0.61
     Salts
    0.61
     tandem
    0.61
    POSITIVE LOGITS
    Could
    1.21
    Sorry
    1.15
    Have
    1.11
    Where
    1.11
    Would
    1.07
    Not
    1.01
    Remove
    1.00
    We
    1.00
    Do
    0.99
    Which
    0.98
    Act Density 0.000%

    No Known Activations