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

    Neuronpedia

    INDEX
    Explanations

    clinical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    模型
    -0.07
    试
    -0.07
     транспор
    -0.07
    mek
    -0.07
    	Token
    -0.07
     luckily
    -0.06
     hairstyle
    -0.06
    temps
    -0.06
     McCabe
    -0.06
     Luckily
    -0.06
    POSITIVE LOGITS
     physical
    0.06
     curse
    0.06
    (case
    0.06
    thood
    0.06
    .Actions
    0.06
     midpoint
    0.06
    (LP
    0.06
     precursor
    0.06
    lemn
    0.06
    -job
    0.06
    Act Density 0.012%

    No Known Activations