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

    Neuronpedia

    INDEX
    Explanations

    codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()])↵
    -0.06
    NAS
    -0.06
     briefly
    -0.06
    _MAY
    -0.06
     STRICT
    -0.06
    icide
    -0.06
    	JButton
    -0.06
    overrides
    -0.06
     world
    -0.06
     territory
    -0.06
    POSITIVE LOGITS
    finding
    0.07
    ��
    0.07
    abil
    0.06
     mixes
    0.06
    prop
    0.06
    affe
    0.06
     sez
    0.06
    ับผ
    0.06
    mî
    0.06
    akens
    0.06
    Act Density 0.015%

    No Known Activations