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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _DEF
    -0.07
    าษ
    -0.06
    avigator
    -0.06
     ماشین
    -0.06
    (food
    -0.06
    eeper
    -0.06
     นาง
    -0.06
    Tenant
    -0.06
    	vec
    -0.06
     x
    -0.06
    POSITIVE LOGITS
     ([[
    0.08
     �
    0.07
    _cancel
    0.07
     made
    0.07
    τά
    0.06
     (@
    0.06
    sis
    0.06
    leine
    0.06
    ầm
    0.06
    上が
    0.06
    Act Density 0.045%

    No Known Activations