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

    Neuronpedia

    INDEX
    Explanations

    harmful or offensive statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     çöz
    0.41
    Seamless
    0.41
     optimized
    0.39
    Solutions
    0.39
     multist
    0.39
     जटिल
    0.38
    SOLUTION
    0.38
     구축
    0.37
     risolvere
    0.37
     حل
    0.37
    POSITIVE LOGITS
     utterances
    1.55
     statements
    1.53
     utterance
    1.46
     comments
    1.38
     выска
    1.37
     remarks
    1.36
     Statements
    1.34
     uttered
    1.32
    Statements
    1.28
    statements
    1.27
    Act Density 0.090%

    No Known Activations