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

    Neuronpedia

    INDEX
    Explanations

    Hartree-Fock simulations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    चित्र
    0.45
     ہزار
    0.41
     королев
    0.41
    كان
    0.40
    独自
    0.40
    ён
    0.39
    कल
    0.39
    мона
    0.39
    售价
    0.38
    لون
    0.38
    POSITIVE LOGITS
     simulator
    0.48
     bases
    0.48
     simulations
    0.47
     simulators
    0.46
    ベース
    0.45
     Simulations
    0.45
     Simulator
    0.44
     kinetics
    0.44
     simulation
    0.43
     simulating
    0.43
    Act Density 0.000%

    No Known Activations