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

    Neuronpedia

    INDEX
    Explanations

    idealizing someone/pedestal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dominic
    -0.07
    دام
    -0.07
     Ship
    -0.07
    .slim
    -0.07
    iff
    -0.06
    .Download
    -0.06
     Dah
    -0.06
    úp
    -0.06
     overnight
    -0.06
    .Autowired
    -0.06
    POSITIVE LOGITS
     obce
    0.07
     daň
    0.07
    :[
    0.07
    』↵↵
    0.06
    ++;↵↵
    0.06
     flawed
    0.06
    /$',
    0.06
     abusing
    0.06
     renovation
    0.06
    ");
↵
↵
    0.06
    Act Density 0.083%

    No Known Activations