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

    Neuronpedia

    INDEX
    Explanations

    general techniques, for the, in interplay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    з
    0.80
    ﺑ
    0.76
    ಟೆ
    0.75
    pillar
    0.73
    டன்
    0.73
    ב
    0.73
    ble
    0.70
    가가
    0.70
    zinha
    0.68
     кноп
    0.68
    POSITIVE LOGITS
    দৃষ্টি
    0.86
    始め
    0.81
    装備
    0.80
     procrast
    0.80
    際は
    0.78
     covariant
    0.77
     nutshell
    0.77
     covariates
    0.77
    ()=>{
    0.76
     centrifug
    0.76
    Act Density 0.000%

    No Known Activations