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

    Neuronpedia

    INDEX
    Explanations

    claims, requests, reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ultural
    -0.08
    )==
    -0.08
     dne
    -0.07
    .pres
    -0.07
     abolition
    -0.07
     Ста
    -0.07
     stom
    -0.07
    Na
    -0.07
    add
    -0.06
     vše
    -0.06
    POSITIVE LOGITS
    _Parse
    0.06
     nic
    0.06
    updating
    0.06
    �
    0.06
    钟
    0.06
    _bind
    0.06
    asmine
    0.06
     مقاله
    0.06
     Wired
    0.05
    0.05
    Act Density 0.001%

    No Known Activations