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

    Neuronpedia

    INDEX
    Explanations

    definitions and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ставак
    0.57
     videomuz
    0.52
     vehicula
    0.52
    㠻
    0.52
     ähm
    0.52
     adimensional
    0.52
     artículos
    0.51
     සිදු
    0.48
     počet
    0.48
     Mitgl
    0.48
    POSITIVE LOGITS
    im
    0.60
    that
    0.53
    8
    0.52
     '
    0.51
     that
    0.50
    expression
    0.49
    desired
    0.49
     Happy
    0.49
    ico
    0.49
    ld
    0.48
    Act Density 0.000%

    No Known Activations