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

    Neuronpedia

    INDEX
    Explanations

    here

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -equipped
    -0.07
     вместе
    -0.07
    Eventually
    -0.07
    手続き
    -0.07
     nye
    -0.07
     jurisdiction
    -0.07
    meg
    -0.07
     prol
    -0.07
    伤口
    -0.07
    𝓊
    -0.07
    POSITIVE LOGITS
     Tim
    0.07
    VT
    0.07
    变换
    0.06
     MASK
    0.06
    ?\
    0.06
     Ping
    0.06
     QE
    0.06
    㟁
    0.06
    ｠
    0.06
     Hind
    0.06
    Act Density 0.001%

    No Known Activations