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

    Neuronpedia

    INDEX
    Explanations

    cyberbullying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    รรม
    0.40
     sư
    0.38
     Afterwards
    0.38
     harmed
    0.37
     ल्या
    0.36
     softens
    0.36
    FindingsRequest
    0.36
     코드
    0.36
    _{[
    0.35
    داری
    0.35
    POSITIVE LOGITS
    uangan
    0.41
     library
    0.40
    SELECT
    0.39
     toon
    0.38
    libraries
    0.38
     multipurpose
    0.38
    Libraries
    0.37
    Variation
    0.37
    甲
    0.37
     Spoon
    0.37
    Act Density 0.000%

    No Known Activations