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

    Neuronpedia

    INDEX
    Explanations

    astronomical/navigational terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    m
    0.65
     Altos
    0.51
     platelets
    0.50
     శాతం
    0.49
     Safer
    0.47
     plates
    0.47
    보니
    0.46
     racines
    0.46
    mec
    0.46
    সভার
    0.45
    POSITIVE LOGITS
    Hed
    0.52
    Hiking
    0.46
    Methods
    0.45
    Initial
    0.45
    Heart
    0.45
    Providing
    0.43
    ]).
    0.42
     контро
    0.42
    Prior
    0.41
    任務
    0.41
    Act Density 0.000%

    No Known Activations