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

    Neuronpedia

    INDEX
    Explanations

    fault

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .iter
    -0.08
    リ
    -0.07
     إ
    -0.07
    σεων
    -0.07
    317
    -0.07
     Kis
    -0.07
    ERA
    -0.07
    纸
    -0.07
     adrenaline
    -0.07
    ृष
    -0.07
    POSITIVE LOGITS
     Fault
    0.09
     fault
    0.09
    Fault
    0.08
     Rogue
    0.07
    onte
    0.07
     flaws
    0.07
     flawed
    0.06
    fault
    0.06
     scrut
    0.06
     faults
    0.06
    Act Density 0.012%

    No Known Activations