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

    Neuronpedia

    INDEX
    Explanations

    interruption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    젔
    -0.07
     поиск
    -0.07
    付け
    -0.07
    DXVECTOR
    -0.07
    ᴙ
    -0.07
    坋
    -0.07
    média
    -0.07
    徛
    -0.07
    .SEVERE
    -0.06
     verso
    -0.06
    POSITIVE LOGITS
    cannot
    0.08
     Implements
    0.07
    (`↵
    0.07
     Р
    0.07
     deepest
    0.07
    	Destroy
    0.07
    ■
    0.07
    .conn
    0.06
     NOT
    0.06
     Tales
    0.06
    Act Density 0.000%

    No Known Activations