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

    Neuronpedia

    INDEX
    Explanations

    .class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    De
    -0.06
    lero
    -0.06
    -sw
    -0.06
    Trivia
    -0.06
     redundancy
    -0.06
    Br
    -0.06
    	sp
    -0.06
     чаще
    -0.06
    .SEVER
    -0.06
    dma
    -0.06
    POSITIVE LOGITS
    /back
    0.08
     supernatural
    0.08
     awarded
    0.07
     Treaty
    0.07
    INTERFACE
    0.07
    _SEND
    0.07
     واب
    0.07
     INCLUDING
    0.07
     contacted
    0.07
    ESP
    0.07
    Act Density 0.003%

    No Known Activations