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

    Neuronpedia

    INDEX
    Explanations

    made

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pity
    -0.06
     том
    -0.06
    聯
    -0.06
    THING
    -0.06
     Sergei
    -0.06
    FLICT
    -0.06
    шев
    -0.06
    луж
    -0.06
    iti
    -0.06
    bas
    -0.06
    POSITIVE LOGITS
    /Gate
    0.07
     addslashes
    0.07
    �
    0.06
    .samples
    0.06
    ycler
    0.06
     mutual
    0.06
     surely
    0.06
    ='".$_
    0.06
     nécessaire
    0.06
     ctype
    0.06
    Act Density 0.000%

    No Known Activations