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

    Neuronpedia

    INDEX
    Explanations

    snippet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forget
    -0.07
    MatrixXd
    -0.07
    {}'.
    -0.06
     Assumes
    -0.06
     listOf
    -0.06
     ideally
    -0.06
    (conf
    -0.06
    .valueOf
    -0.06
    ृष
    -0.06
    fstream
    -0.06
    POSITIVE LOGITS
     hydr
    0.08
     MAT
    0.07
     мне
    0.07
     Investigations
    0.06
     cargo
    0.06
     Debt
    0.06
    ↵		↵
    0.06
     inland
    0.06
     HUD
    0.06
    attle
    0.06
    Act Density 0.002%

    No Known Activations