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

    Neuronpedia

    INDEX
    Explanations

    solid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mani
    -0.07
     creek
    -0.06
    цями
    -0.06
    	menu
    -0.06
     kanun
    -0.06
     возникнов
    -0.06
    	vec
    -0.06
     communicates
    -0.06
    ely
    -0.06
    Startup
    -0.06
    POSITIVE LOGITS
     Hard
    0.08
     solids
    0.08
    hai
    0.07
    /ad
    0.07
    ursos
    0.07
    agr
    0.07
     Americas
    0.06
     apology
    0.06
    .ro
    0.06
    .long
    0.06
    Act Density 0.011%

    No Known Activations