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

    Neuronpedia

    INDEX
    Explanations

    references to blueprints or plans

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

    blueprint and Maven projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*
    -0.52
     varones
    -0.50
     terceira
    -0.50
     tasas
    -0.49
     gehad
    -0.49
     médicale
    -0.49
     feminina
    -0.49
     vacas
    -0.48
     casada
    -0.47
     Meeres
    -0.47
    POSITIVE LOGITS
     blueprint
    2.08
     Blueprint
    1.98
    blueprint
    1.73
     blueprints
    1.71
    Blueprint
    1.68
     plan
    0.89
     plans
    0.77
    plan
    0.77
    Plan
    0.72
     ſche
    0.72
    Act Density 0.001%

    No Known Activations