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

    Neuronpedia

    INDEX
    Explanations

    persistence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    composed
    -0.06
    ラ
    -0.06
     Zem
    -0.06
    rowth
    -0.06
    slider
    -0.06
    raf
    -0.06
    inp
    -0.06
    -know
    -0.06
    XA
    -0.06
    _rw
    -0.06
    POSITIVE LOGITS
     perseverance
    0.10
     eskorte
    0.06
    	SDL
    0.06
     Hon
    0.06
     stej
    0.06
     persever
    0.06
     har
    0.06
    ersh
    0.06
    Directories
    0.06
     wooden
    0.06
    Act Density 0.011%

    No Known Activations