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

    Neuronpedia

    INDEX
    Explanations

    Responding to ransomware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     powering
    0.40
     mortals
    0.39
     payable
    0.38
     indulge
    0.38
     gula
    0.38
     setIs
    0.37
     vivre
    0.37
    禇
    0.36
     কুক
    0.36
     gols
    0.36
    POSITIVE LOGITS
    出现在
    0.44
     Quar
    0.43
     Pinch
    0.42
     Rod
    0.39
    Rod
    0.39
    epoch
    0.39
     Brewster
    0.38
    aluminum
    0.38
    ↵↵↵↵↵↵↵↵
    0.37
     pinch
    0.37
    Act Density 0.000%

    No Known Activations