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

    Neuronpedia

    INDEX
    Explanations

    multiple choice options

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    าะ
    -0.08
    zí
    -0.08
     unfore
    -0.08
    utorial
    -0.08
     Festa
    -0.08
    فو
    -0.08
     multid
    -0.07
     unforeseen
    -0.07
    Programming
    -0.07
     لما
    -0.07
    POSITIVE LOGITS
     proposées
    0.11
     proposés
    0.10
     proposed
    0.10
     Proposed
    0.09
     propuestas
    0.09
    candidate
    0.08
     proposé
    0.08
     кандид
    0.08
     hypotheses
    0.08
     candidats
    0.08
    Act Density 0.023%

    No Known Activations