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

    Neuronpedia

    INDEX
    Explanations

    atomic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erver
    -0.09
    Ev
    -0.08
    Scroll
    -0.08
     Eve
    -0.08
    𝐷
    -0.08
    eto
    -0.07
    涼
    -0.07
    舒
    -0.07
    .SystemColors
    -0.07
    很棒
    -0.07
    POSITIVE LOGITS
    .atomic
    0.08
    tat
    0.07
    	hit
    0.07
     [-]:
    0.07
    .bit
    0.07
     importantly
    0.07
    "}}
    0.07
    عاط
    0.07
     hugged
    0.07
    .Atomic
    0.06
    Act Density 0.006%

    No Known Activations