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

    Neuronpedia

    INDEX
    Explanations

    menu, navigation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🤘
    -0.09
     CACHE
    -0.08
    萚
    -0.07
     сфере
    -0.07
    小时
    -0.07
    deployment
    -0.07
    зван
    -0.07
     USERNAME
    -0.07
    大理石
    -0.07
    𝜙
    -0.07
    POSITIVE LOGITS
     timid
    0.07
    Instances
    0.07
    enza
    0.07
    Sch
    0.07
     Más
    0.07
     effects
    0.06
    ent
    0.06
    	ent
    0.06
     conditioning
    0.06
     Anxiety
    0.06
    Act Density 0.010%

    No Known Activations