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

    Neuronpedia

    INDEX
    Explanations

    code with conditional statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _single
    -0.07
    看见
    -0.07
    supply
    -0.07
    holders
    -0.06
    _Message
    -0.06
     Species
    -0.06
    ｊ
    -0.06
    Incoming
    -0.06
     бесп
    -0.06
     acidic
    -0.06
    POSITIVE LOGITS
    どう
    0.07
    	score
    0.07
     blacks
    0.07
    +,
    0.06
    >Email
    0.06
    }]
    0.06
    acic
    0.06
     ingl
    0.06
    、どう
    0.06
     knock
    0.06
    Act Density 0.011%

    No Known Activations