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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    moire
    -0.08
    matches
    -0.07
    üyordu
    -0.07
     ATF
    -0.07
    /nav
    -0.07
     entreg
    -0.07
    ))),
    -0.07
     compens
    -0.06
    )set
    -0.06
    .failed
    -0.06
    POSITIVE LOGITS
    سة
    0.07
     pointers
    0.06
    utting
    0.06
    室
    0.06
    TY
    0.06
    价
    0.06
    _cells
    0.06
    _distances
    0.05
    _roll
    0.05
    用的
    0.05
    Act Density 0.024%

    No Known Activations