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

    Neuronpedia

    INDEX
    Explanations

    asking you about travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻭ
    1.70
    Verifier
    1.63
    Decimal
    1.52
     राणा
    1.49
     MANAGER
    1.48
    Iterable
    1.48
     Decimal
    1.46
    ovány
    1.46
    ི་
    1.44
    ﻴ
    1.43
    POSITIVE LOGITS
     reto
    1.01
     pret
    0.99
    street
    0.95
    ET
    0.93
     street
    0.89
    ;_
    0.88
     pitched
    0.88
     poh
    0.88
     mancan
    0.86
     ro
    0.84
    Act Density 0.000%

    No Known Activations