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

    Neuronpedia

    INDEX
    Explanations

    risk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    赤
    -0.07
     llama
    -0.07
     mph
    -0.07
     слід
    -0.06
     swiper
    -0.06
     Forrest
    -0.06
     ปร
    -0.06
     attendant
    -0.06
     dataGridViewTextBoxColumn
    -0.06
     maur
    -0.06
    POSITIVE LOGITS
     risk
    0.09
     Risk
    0.08
    [N
    0.07
    -risk
    0.07
    -trained
    0.07
    Command
    0.06
     rhe
    0.06
     ČR
    0.06
    _DEPRECATED
    0.06
    Check
    0.06
    Act Density 0.004%

    No Known Activations