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

    Neuronpedia

    INDEX
    Explanations

    ]:

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RAY
    -0.08
     sexual
    -0.07
    _WIN
    -0.07
     kì
    -0.07
    诎
    -0.07
    URRED
    -0.07
    ギャ
    -0.06
    .java
    -0.06
    EATURE
    -0.06
     Neuro
    -0.06
    POSITIVE LOGITS
    כרטיס
    0.07
    ates
    0.06
    批复
    0.06
     helf
    0.06
    oll
    0.06
    ­i
    0.06
    	default
    0.06
    antage
    0.06
    itations
    0.06
    \base
    0.06
    Act Density 0.001%

    No Known Activations