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

    Neuronpedia

    INDEX
    Explanations

    tokenizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     differentiating
    0.45
     enabling
    0.44
     nodding
    0.44
     contingency
    0.42
     supervision
    0.41
     dredging
    0.41
    られました
    0.40
     shelved
    0.40
     clauses
    0.39
     cargoes
    0.39
    POSITIVE LOGITS
     équip
    0.44
    stop
    0.40
    And
    0.39
     பொறிய
    0.39
     Have
    0.39
     deteriorate
    0.38
    exempl
    0.37
     Shoot
    0.37
     électron
    0.37
    Autow
    0.37
    Act Density 0.000%

    No Known Activations