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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    앞
    -0.08
     impotence
    -0.08
     lore
    -0.08
     devant
    -0.08
    	throws
    -0.08
     مربوط
    -0.08
     đổi
    -0.08
    .definition
    -0.08
     introd
    -0.07
     definitions
    -0.07
    POSITIVE LOGITS
     preferably
    0.14
    recommended
    0.12
     suitable
    0.12
     advisable
    0.11
     recommended
    0.11
     prefer
    0.11
    Recommendation
    0.10
     recomendamos
    0.10
    prefer
    0.10
     recommend
    0.10
    Act Density 0.060%

    No Known Activations