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

    Neuronpedia

    INDEX
    Explanations

    eradication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Nİ
    -0.07
     이야기
    -0.06
     ])
    -0.06
    :first
    -0.06
     aloud
    -0.06
     Initialized
    -0.06
     RAD
    -0.06
    ]))↵↵
    -0.06
     selfies
    -0.06
    νης
    -0.06
    POSITIVE LOGITS
     erad
    0.07
    .maps
    0.06
     eradicate
    0.06
     eliminating
    0.06
     Engineer
    0.06
    xxxx
    0.06
    Anchor
    0.06
    304
    0.06
     Hardy
    0.06
    	point
    0.06
    Act Density 0.016%

    No Known Activations