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

    Neuronpedia

    INDEX
    Explanations

    rape routine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PMI
    0.40
    ΜΑ
    0.38
    pmap
    0.36
     চাঁদ
    0.36
    owała
    0.35
     बाहेर
    0.34
     اولمپ
    0.33
    jala
    0.33
    Mana
    0.33
     rejuvenate
    0.32
    POSITIVE LOGITS
    दिष्ट
    0.38
     Trunk
    0.38
    eken
    0.37
     Modules
    0.36
     интеллектуа
    0.36
     Swift
    0.35
     SignUp
    0.35
     shields
    0.34
     dank
    0.34
    ល់
    0.34
    Act Density 0.000%

    No Known Activations