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

    Neuronpedia

    INDEX
    Explanations

    warm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     warm
    -1.07
    mystery
    -1.01
    warm
    -0.99
     Warm
    -0.98
    Warm
    -0.96
     mystery
    -0.94
     warmer
    -0.94
     warmed
    -0.85
     WARM
    -0.85
     varmt
    -0.85
    POSITIVE LOGITS
    ness
    0.79
    NESS
    0.56
     utafitiHapana
    0.54
     points
    0.53
     point
    0.52
    iness
    0.50
    nesses
    0.50
     waters
    0.48
     spot
    0.47
    ترین
    0.46
    Act Density 0.045%

    No Known Activations