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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bieber
    -0.07
    	curl
    -0.06
     nit
    -0.06
    -spinner
    -0.06
     chang
    -0.06
    ันก
    -0.06
     bothers
    -0.06
    _COLLECTION
    -0.06
    онь
    -0.06
     ambassador
    -0.06
    POSITIVE LOGITS
    电话
    0.07
     ka
    0.07
     premiere
    0.06
    解决
    0.06
    张
    0.06
    gons
    0.06
     chatte
    0.06
    _gen
    0.06
     er
    0.06
    0.06
    Act Density 0.009%

    No Known Activations