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

    Neuronpedia

    INDEX
    Explanations

    child sexual abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ATC
    0.38
     undergo
    0.37
    zeniach
    0.37
     sukar
    0.37
     suitable
    0.36
     forms
    0.36
    不像
    0.36
    ത്തിലൂടെ
    0.35
     příst
    0.35
     case
    0.35
    POSITIVE LOGITS
    谯
    0.41
    Prepar
    0.40
    दरअसल
    0.40
    \"\
    0.39
    ドウ
    0.38
     Prefeitura
    0.37
    ম্মদ
    0.37
     леп
    0.37
    क्षत्र
    0.37
    赉
    0.37
    Act Density 0.004%

    No Known Activations