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

    Neuronpedia

    INDEX
    Explanations

    relationship advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orso
    0.43
     CS
    0.42
    CS
    0.40
     Sensor
    0.40
    assignment
    0.39
     assignment
    0.39
     CSF
    0.39
    センサー
    0.39
     shocking
    0.38
     coleg
    0.38
    POSITIVE LOGITS
     Affairs
    0.42
     fnt
    0.42
     구해
    0.40
     trav
    0.37
     autof
    0.37
     “.
    0.36
    Всім
    0.36
    給大家
    0.35
    ванне
    0.35
    пе
    0.35
    Act Density 0.000%

    No Known Activations