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

    Neuronpedia

    INDEX
    Explanations

    building and creating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (grammar
    -0.07
     profound
    -0.07
    悠
    -0.06
    _ros
    -0.06
    _WEAPON
    -0.06
    .median
    -0.06
     цель
    -0.06
            ↵↵
    -0.06
    _EX
    -0.06
     Honor
    -0.06
    POSITIVE LOGITS
    jab
    0.07
    isinde
    0.06
    abilidade
    0.06
    ayet
    0.06
    mite
    0.06
    enght
    0.06
    -ci
    0.06
    łem
    0.06
    _PRICE
    0.06
    amba
    0.06
    Act Density 0.019%

    No Known Activations