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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Comm
    -0.08
     zaj
    -0.07
    商务
    -0.07
     hydrogen
    -0.07
    sed
    -0.07
    純
    -0.06
     tcp
    -0.06
    additional
    -0.06
    נע
    -0.06
    ByUsername
    -0.06
    POSITIVE LOGITS
    瓣
    0.08
    扇
    0.07
    一手
    0.07
    でしょう
    0.06
    危机
    0.06
     viele
    0.06
     shovel
    0.06
    /copyleft
    0.06
     reefs
    0.06
    _GF
    0.06
    Act Density 0.069%

    No Known Activations