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

    Neuronpedia

    INDEX
    Explanations

    sounds like enthusiastic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gait
    0.54
     stakeholders
    0.54
     widget
    0.54
     week
    0.53
    ក៏
    0.52
     country
    0.52
    PERATURE
    0.52
     ADJUST
    0.52
    I
    0.51
     data
    0.50
    POSITIVE LOGITS
     защиту
    0.59
    Prote
    0.58
    Arm
    0.55
    䁂
    0.55
    Fail
    0.53
    تر
    0.53
     Versorgung
    0.53
    protection
    0.52
    ست
    0.52
    ینه
    0.52
    Act Density 0.000%

    No Known Activations