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

    Neuronpedia

    INDEX
    Explanations

    code, math, cell, strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maver
    0.84
     Navarro
    0.82
     Sharp
    0.81
     scorpion
    0.80
     MAK
    0.79
     Peacock
    0.78
     Sweep
    0.78
     Palma
    0.77
    powerm
    0.77
    μ
    0.77
    POSITIVE LOGITS
     DOT
    0.90
     Zel
    0.82
     Nit
    0.80
     Krug
    0.80
     Liter
    0.79
     Lit
    0.75
    DOT
    0.74
     Zon
    0.72
    Lit
    0.72
     liter
    0.72
    Act Density 1.487%

    No Known Activations