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

    Neuronpedia

    INDEX
    Explanations

    anti

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    קוד
    -0.08
    홋
    -0.07
    ollectors
    -0.07
    reservation
    -0.07
    𐰰
    -0.07
     Bunifu
    -0.07
    .rm
    -0.07
     conflic
    -0.07
    멕
    -0.07
    _PIXEL
    -0.07
    POSITIVE LOGITS
     anti
    0.10
     conduct
    0.08
    taskId
    0.08
    Anti
    0.07
    ltra
    0.07
    ца
    0.07
    Nu
    0.07
     또
    0.07
    	snprintf
    0.07
    anti
    0.07
    Act Density 0.013%

    No Known Activations