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

    Neuronpedia

    INDEX
    Explanations

    rolling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Arrays
    -0.07
    ically
    -0.07
     cabin
    -0.07
     seniors
    -0.06
     strtolower
    -0.06
    �
    -0.06
     Sok
    -0.06
    .tim
    -0.06
    	ch
    -0.06
    _n
    -0.06
    POSITIVE LOGITS
     konum
    0.07
    ril
    0.06
     considerable
    0.06
     Voj
    0.06
     choisir
    0.06
    -être
    0.06
    ermann
    0.06
    іла
    0.05
    thood
    0.05
    Ring
    0.05
    Act Density 0.000%

    No Known Activations