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

    Neuronpedia

    INDEX
    Explanations

    Internet forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANTA
    -0.08
    Dest
    -0.07
    gunta
    -0.07
     chim
    -0.07
     Dakota
    -0.06
     aku
    -0.06
     Dest
    -0.06
    dac
    -0.06
     recom
    -0.06
    	draw
    -0.06
    POSITIVE LOGITS
    .collections
    0.06
    .property
    0.06
    λό
    0.06
    esion
    0.06
    \"></
    0.06
     hindsight
    0.06
    がある
    0.06
    mez
    0.06
    ь
    0.06
     Велик
    0.06
    Act Density 0.069%

    No Known Activations