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

    Neuronpedia

    INDEX
    Explanations

    we propose introducing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ideally
    0.45
     потребности
    0.45
     esperamos
    0.45
     subjunctive
    0.42
    需求的
    0.41
     saturation
    0.41
     razum
    0.40
     bisogno
    0.40
     qualitative
    0.39
     convenience
    0.39
    POSITIVE LOGITS
     proposed
    1.37
     proposes
    1.27
     propose
    1.25
    proposed
    1.23
     proposto
    1.20
     proposing
    1.18
     Proposed
    1.17
     proposta
    1.15
     proposé
    1.14
    提出
    1.13
    Act Density 0.022%

    No Known Activations