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

    Neuronpedia

    INDEX
    Explanations

    exploitation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obic
    -0.07
     умов
    -0.06
     cosy
    -0.06
    refix
    -0.06
     contagious
    -0.06
     newObj
    -0.06
    HONE
    -0.06
    ERNEL
    -0.06
     jej
    -0.06
    でしょう
    -0.06
    POSITIVE LOGITS
     exploit
    0.09
     exploitation
    0.09
     exploiting
    0.08
     abusive
    0.07
     explo
    0.07
     exploited
    0.07
    -P
    0.07
     advantage
    0.06
    ":"+
    0.06
    ★★
    0.06
    Act Density 0.011%

    No Known Activations