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

    Neuronpedia

    INDEX
    Explanations

    via

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aimassage
    -0.07
     Hands
    -0.07
    Bas
    -0.06
     территор
    -0.06
    AES
    -0.06
    (Index
    -0.06
    reas
    -0.06
    })();
    -0.06
    แปลง
    -0.06
     Weld
    -0.06
    POSITIVE LOGITS
     freel
    0.07
     عليك
    0.07
     affili
    0.07
     شهری
    0.06
    вей
    0.06
    _front
    0.06
     toward
    0.06
     getPassword
    0.06
    ;:;:
    0.06
    .CONFIG
    0.06
    Act Density 0.002%

    No Known Activations