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

    Neuronpedia

    INDEX
    Explanations

    welcome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zus
    -0.06
     poo
    -0.06
    damage
    -0.06
    dw
    -0.06
    Loc
    -0.06
    _tau
    -0.06
    *e
    -0.06
    (label
    -0.06
    .dsl
    -0.06
     Lawson
    -0.06
    POSITIVE LOGITS
    영
    0.08
    เทศ
    0.07
    .direct
    0.07
    	bg
    0.07
    _FETCH
    0.07
     explore
    0.07
    rote
    0.07
     mechanisms
    0.07
    읍
    0.06
    _rooms
    0.06
    Act Density 0.002%

    No Known Activations