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

    Neuronpedia

    INDEX
    Explanations

    disk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    选�
    -0.07
    arity
    -0.06
    setTimeout
    -0.06
    努力
    -0.06
    joint
    -0.06
    оре
    -0.06
     нічого
    -0.06
     Categories
    -0.06
    _ENTRY
    -0.06
    iscrimination
    -0.06
    POSITIVE LOGITS
     disc
    0.11
     disks
    0.10
     discs
    0.09
     disk
    0.09
     Disk
    0.08
     disreg
    0.07
    mis
    0.07
    š
    0.07
    ovic
    0.07
    dc
    0.07
    Act Density 0.003%

    No Known Activations