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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frid
    -0.06
     Raid
    -0.06
     Frequently
    -0.06
    .COLUMN
    -0.06
    ependency
    -0.06
    masından
    -0.06
     бер
    -0.06
    perience
    -0.06
    .FIELD
    -0.06
     teamwork
    -0.06
    POSITIVE LOGITS
    _SAFE
    0.07
     zoals
    0.07
    麗
    0.07
    Ash
    0.06
     bailout
    0.06
     jump
    0.06
     Pistol
    0.06
    .tree
    0.06
    offset
    0.06
     firstly
    0.06
    Act Density 0.001%

    No Known Activations