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

    Neuronpedia

    INDEX
    Explanations

    geometric segments and distances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dent
    0.46
    гыз
    0.40
    Http
    0.40
    Makeup
    0.40
    Sends
    0.40
    assam
    0.39
    ahit
    0.39
     मध्या
    0.39
    拶
    0.38
    Hyd
    0.38
    POSITIVE LOGITS
     AB
    1.03
     AC
    0.80
     BC
    0.78
     ABC
    0.76
    AB
    0.75
     CD
    0.67
     segment
    0.64
     ABCD
    0.63
     BA
    0.61
     एबी
    0.61
    Act Density 0.005%

    No Known Activations