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

    Neuronpedia

    INDEX
    Explanations

    Phone numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wend
    -0.07
     nghị
    -0.07
    Option
    -0.07
     concurrent
    -0.07
    Roger
    -0.07
    rones
    -0.07
    acro
    -0.06
     PASSWORD
    -0.06
     Tian
    -0.06
    slash
    -0.06
    POSITIVE LOGITS
    .medium
    0.06
    pecting
    0.06
    _MAPPING
    0.06
    -random
    0.06
     буду
    0.06
    /bower
    0.06
     보고
    0.06
     جمهوری
    0.06
     hlas
    0.05
     geldi
    0.05
    Act Density 0.005%

    No Known Activations