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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Know
    -0.07
     love
    -0.07
    vail
    -0.07
     Triangle
    -0.07
    Think
    -0.06
    ayd
    -0.06
    	on
    -0.06
    ,omitempty
    -0.06
     six
    -0.06
     lĩnh
    -0.06
    POSITIVE LOGITS
     Нас
    0.07
    etyl
    0.07
    olation
    0.07
    -aligned
    0.06
    cale
    0.06
    alars
    0.06
    ensing
    0.06
     calor
    0.06
    ünst
    0.06
    Filters
    0.06
    Act Density 0.033%

    No Known Activations