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

    Neuronpedia

    INDEX
    Explanations

    sinking/physics problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Grou
    -0.08
    GROUP
    -0.08
     GROUP
    -0.08
     jungle
    -0.08
     hurdle
    -0.08
     midfield
    -0.08
     evangel
    -0.07
    _LEVEL
    -0.07
     broadcasting
    -0.07
     FIRE
    -0.07
    POSITIVE LOGITS
     Δ
    0.13
    Δ
    0.11
    (delta
    0.11
     centimeters
    0.11
     displacement
    0.11
     deformation
    0.10
     δ
    0.10
    毫米
    0.10
    ∆
    0.10
     delta
    0.09
    Act Density 0.016%

    No Known Activations