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

    Neuronpedia

    INDEX
    Explanations

    harmful or malicious content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    豁
    0.43
     সংক্রমণ
    0.42
     kämp
    0.38
    LLCATS
    0.38
     Gagn
    0.38
     Wyndham
    0.37
     সংক্রমণের
    0.37
    Soc
    0.36
     sterilization
    0.36
     ചരി
    0.36
    POSITIVE LOGITS
     teenagers
    0.38
     रव
    0.37
    jing
    0.37
     ते
    0.36
    Smart
    0.36
    INESS
    0.36
     stimuli
    0.36
     Broken
    0.36
     ideia
    0.36
    Stopping
    0.36
    Act Density 0.000%

    No Known Activations