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

    Neuronpedia

    INDEX
    Explanations

    competitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nitrogen
    -0.08
    _O
    -0.07
     Hod
    -0.06
    .Gen
    -0.06
     '=
    -0.06
    _d
    -0.06
     polymer
    -0.06
     delivers
    -0.06
    Train
    -0.06
     dend
    -0.06
    POSITIVE LOGITS
     florida
    0.07
    RTOS
    0.07
    blog
    0.07
    ᾄ
    0.07
    RIX
    0.07
    嗣
    0.07
    比べ
    0.07
     firefox
    0.06
    uced
    0.06
    edException
    0.06
    Act Density 0.010%

    No Known Activations