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

    Neuronpedia

    INDEX
    Explanations

    logical conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plantation
    -0.10
     Plantation
    -0.09
     mani
    -0.09
     plantations
    -0.08
     прогул
    -0.08
     기타
    -0.08
     socials
    -0.08
    _BORDER
    -0.08
     strolling
    -0.07
     renovations
    -0.07
    POSITIVE LOGITS
     منط
    0.08
     fault
    0.08
     complement
    0.08
     cycles
    0.08
     causal
    0.07
     ubiquit
    0.07
    0.07
     ciclos
    0.07
    周期
    0.07
     attribute
    0.07
    Act Density 0.020%
    No Known Activations