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

    Neuronpedia

    INDEX
    Explanations

    technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    癀
    -0.09
    apeutics
    -0.08
    dfd
    -0.07
    фин
    -0.07
    닿
    -0.06
     saliva
    -0.06
    仂
    -0.06
    _representation
    -0.06
    	NullCheck
    -0.06
    🚀
    -0.06
    POSITIVE LOGITS
     locality
    0.07
    观念
    0.07
    ROLLER
    0.07
     contested
    0.07
    ylinder
    0.07
    pective
    0.07
     batch
    0.07
    .Packet
    0.07
     Belt
    0.07
     תמונה
    0.06
    Act Density 0.007%

    No Known Activations