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

    Neuronpedia

    INDEX
    Explanations

    preload

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ñ
    -0.08
     Indices
    -0.06
    ною
    -0.06
    úmeros
    -0.06
    lea
    -0.06
     UserInfo
    -0.06
    illon
    -0.06
    یتی
    -0.06
    }},
    -0.06
     delet
    -0.06
    POSITIVE LOGITS
     distributor
    0.08
    -fly
    0.07
    ;</
    0.06
     PRIV
    0.06
    804
    0.06
     Lottery
    0.06
     وص
    0.06
     cand
    0.06
    	afx
    0.06
     nightmare
    0.06
    Act Density 0.016%

    No Known Activations