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

    Neuronpedia

    INDEX
    Explanations

    ruin reputation relationships health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.43
    rashed
    0.42
    be
    0.41
    menu
    0.39
    os
    0.39
     \
    0.38
    X
    0.38
     X
    0.38
     Who
    0.37
    ka
    0.37
    POSITIVE LOGITS
     reputations
    0.61
     ruining
    0.59
     ruins
    0.56
     irrepar
    0.54
     ruin
    0.53
     jeopard
    0.53
     चौपट
    0.52
     ruined
    0.52
     havoc
    0.51
    破坏
    0.51
    Act Density 0.067%

    No Known Activations