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

    Neuronpedia

    INDEX
    Explanations

    words or phrases that introduce a clarifying or explanatory statement.

    oai_token-act-pair · gemini-2.0-flash

    allow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condensation
    -0.88
     dew
    -0.85
     droplets
    -0.68
     condens
    -0.63
     fog
    -0.60
     sweat
    -0.59
     kond
    -0.59
    sweat
    -0.59
     sweating
    -0.58
     moisture
    -0.58
    POSITIVE LOGITS
     let
    1.16
     allow
    1.05
     Allow
    1.00
    Allow
    0.96
    allow
    0.89
     lemme
    0.88
     permit
    0.85
     Let
    0.84
     ALLOW
    0.81
    Let
    0.80
    Act Density 1.458%

    No Known Activations