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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (dc
    -0.07
    飲
    -0.07
     supervisors
    -0.07
     zpět
    -0.07
     од
    -0.07
     containing
    -0.06
     ήταν
    -0.06
    Cisco
    -0.06
     combinations
    -0.06
    })
↵
    -0.06
    POSITIVE LOGITS
    ocks
    0.07
     Selling
    0.07
    _BOOLEAN
    0.07
    .fasta
    0.06
    SHOT
    0.06
    .exception
    0.06
    imler
    0.06
    ément
    0.06
     UIApplication
    0.06
    elerle
    0.06
    Act Density 0.031%

    No Known Activations