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

    Neuronpedia

    INDEX
    Explanations

    actions and states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     solvents
    0.45
     approachable
    0.43
     blanket
    0.40
     Rivera
    0.40
     solvent
    0.39
     luckily
    0.39
     branched
    0.39
     cyanide
    0.39
     Symp
    0.38
    シェ
    0.38
    POSITIVE LOGITS
    itions
    0.42
    ismus
    0.40
    izações
    0.40
    이제
    0.39
     деятельность
    0.38
    ред
    0.37
    <0xA2>
    0.37
    usch
    0.37
    classAttribute
    0.37
     马
    0.37
    Act Density 0.001%

    No Known Activations