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

    Neuronpedia

    INDEX
    Explanations

    LOCKS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     politico
    0.46
    setKeepCallback
    0.44
     ವರ್ಗ
    0.42
     locali
    0.41
     قرارد
    0.41
     блю
    0.41
    டக்கலை
    0.41
    талия
    0.40
     conserva
    0.40
     politici
    0.40
    POSITIVE LOGITS
     VIA
    0.44
     inv
    0.42
     Inv
    0.41
    耐
    0.40
     via
    0.40
     grom
    0.40
     enabled
    0.38
     pakk
    0.38
     as
    0.38
     breeder
    0.38
    Act Density 0.000%

    No Known Activations