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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "hide" and its variations

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

    hiding things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PhysRev
    -0.58
     Bona
    -0.56
      
    -0.56
     Pong
    -0.50
     Allegro
    -0.50
     Stellar
    -0.50
     Latter
    -0.50
     ECT
    -0.48
     Cey
    -0.48
     Slick
    -0.48
    POSITIVE LOGITS
     hiding
    1.30
    Hiding
    1.12
     Hiding
    1.11
    hiding
    1.11
     esconder
    0.99
     hide
    0.95
     hid
    0.93
     hides
    0.91
     esconde
    0.85
     ocultar
    0.79
    Act Density 0.006%

    No Known Activations