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

    Neuronpedia

    INDEX
    Explanations

    technical/academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ripe
    -0.07
     formed
    -0.06
     wreck
    -0.06
     wipe
    -0.06
    ่าร
    -0.06
    trinsic
    -0.06
     rac
    -0.06
    ベル
    -0.06
    ुल
    -0.06
     rank
    -0.06
    POSITIVE LOGITS
    [last
    0.07
    expression
    0.07
    levant
    0.06
    /Test
    0.06
    知道
    0.06
     Medina
    0.06
     Dost
    0.06
    filename
    0.06
    	block
    0.06
     см
    0.06
    Act Density 0.000%

    No Known Activations