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

    Neuronpedia

    INDEX
    Explanations

    references to specific phases in a process or study

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbered or descriptive phases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Smarty
    -0.37
     australian
    -0.35
     insectos
    -0.34
     Not
    -0.30
     TK
    -0.30
     bra
    -0.29
     scottish
    -0.29
     хранения
    -0.29
    Scri
    -0.28
    Lonely
    -0.28
    POSITIVE LOGITS
     phase
    1.62
     phases
    1.51
     Phase
    1.51
    Phase
    1.48
     Phases
    1.41
     PHASE
    1.40
    phase
    1.38
    phases
    1.34
    PHASE
    1.33
    sphase
    1.30
    Act Density 0.023%

    No Known Activations