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

    Neuronpedia

    INDEX
    Explanations

    clearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     JP
    -0.07
     Sach
    -0.07
    宿
    -0.06
     findById
    -0.06
     因
    -0.06
    Phys
    -0.06
    模
    -0.06
    仪
    -0.06
     HOR
    -0.06
    ISTRY
    -0.06
    POSITIVE LOGITS
     clearance
    0.13
     Clearance
    0.09
     Stateless
    0.07
    mac
    0.07
     blackout
    0.07
    uckland
    0.07
    iedo
    0.06
    kc
    0.06
    startIndex
    0.06
    λά
    0.06
    Act Density 0.002%

    No Known Activations