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

    Neuronpedia

    INDEX
    Explanations

    study them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    в
    0.49
    се
    0.46
    ajit
    0.45
    ча
    0.44
    0.44
    ріа
    0.43
    ownic
    0.43
     للت
    0.42
    ન
    0.41
    u
    0.41
    POSITIVE LOGITS
     thermocouple
    0.46
     Однако
    0.45
     TextBox
    0.43
     Clients
    0.42
     waterway
    0.42
     feedwater
    0.42
     clientId
    0.41
    焓
    0.41
     phonetic
    0.41
    曲線
    0.40
    Act Density 0.002%

    No Known Activations