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

    Neuronpedia

    INDEX
    Explanations

    general information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	mod
    -0.07
    asına
    -0.07
     hitting
    -0.06
    　ｌ
    -0.06
    tractor
    -0.06
    David
    -0.06
    _GE
    -0.06
    eating
    -0.06
    _pb
    -0.06
     установ
    -0.06
    POSITIVE LOGITS
     accusing
    0.07
    .ct
    0.07
     Lug
    0.06
    .realpath
    0.06
    ㅇ
    0.06
    ')==
    0.06
     Reggie
    0.06
     NE
    0.06
     AUG
    0.06
     quarterly
    0.06
    Act Density 0.109%

    No Known Activations