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

    Neuronpedia

    INDEX
    Explanations

    Specific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roosevelt
    -0.07
    astic
    -0.06
     Toilet
    -0.06
     shoe
    -0.06
     plug
    -0.06
    술
    -0.06
    Drag
    -0.06
    activate
    -0.06
    jom
    -0.05
     sour
    -0.05
    POSITIVE LOGITS
     مبانی
    0.07
    erchant
    0.07
    ideon
    0.07
     Compet
    0.07
    _CONF
    0.07
     specifics
    0.06
     strategist
    0.06
    SingleOrDefault
    0.06
    lol
    0.06
    NPC
    0.06
    Act Density 0.036%

    No Known Activations