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

    Neuronpedia

    INDEX
    Explanations

    `---`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     showcased
    0.46
    ifiably
    0.45
    🉑
    0.45
    amsu
    0.45
     opioids
    0.45
     beim
    0.44
     Eich
    0.44
     outcomes
    0.43
    🉐
    0.43
     Lombard
    0.43
    POSITIVE LOGITS
    |\
    0.55
    ----
    0.54
    ----------------
    0.53
    ------------
    0.52
    -----------
    0.51
    -\
    0.49
    山
    0.49
    -------
    0.49
    --------
    0.48
    ||
    0.48
    Act Density 0.549%

    No Known Activations