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

    Neuronpedia

    INDEX
    Explanations

    lump

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (background
    -0.08
     activates
    -0.07
     sharedInstance
    -0.07
    obia
    -0.07
    by
    -0.07
    ane
    -0.07
    xa
    -0.06
     siyasi
    -0.06
    ACE
    -0.06
     staffers
    -0.06
    POSITIVE LOGITS
     lump
    0.12
     Lump
    0.10
     stump
    0.08
    ummings
    0.08
     Hlav
    0.07
     CSP
    0.07
    Tipo
    0.07
    Misc
    0.07
     Lamp
    0.07
    -point
    0.07
    Act Density 0.003%

    No Known Activations