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

    Neuronpedia

    INDEX
    Explanations

    development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     huis
    -0.06
     volum
    -0.06
    cos
    -0.06
     trib
    -0.06
     thay
    -0.06
     Ranked
    -0.06
    orte
    -0.05
    gu
    -0.05
    outube
    -0.05
     discipline
    -0.05
    POSITIVE LOGITS
     Development
    0.08
     development
    0.07
    obraz
    0.07
    -development
    0.07
     �
    0.07
    	lp
    0.07
    PMENT
    0.06
    Aligned
    0.06
    _enter
    0.06
     Jug
    0.06
    Act Density 0.005%

    No Known Activations