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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -now
    -0.07
     cylindrical
    -0.07
    datetime
    -0.06
     lokal
    -0.06
    Daniel
    -0.06
    ไฟ
    -0.06
     dilation
    -0.06
    undred
    -0.06
     ###
    -0.06
     delightful
    -0.06
    POSITIVE LOGITS
     Eth
    0.07
    itr
    0.07
     Corruption
    0.07
     Hep
    0.06
     contractor
    0.06
    apon
    0.06
    	End
    0.06
    Canadian
    0.06
    -G
    0.06
    [:,
    0.06
    Act Density 0.260%

    No Known Activations