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

    Neuronpedia

    INDEX
    Explanations

    least

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     muse
    -0.07
    RoleId
    -0.07
    idas
    -0.06
    >s
    -0.06
     poc
    -0.06
    	entry
    -0.06
    igest
    -0.06
    UPDATE
    -0.06
     getNext
    -0.06
    ée
    -0.06
    POSITIVE LOGITS
    //@
    0.07
    球
    0.07
     college
    0.07
    462
    0.06
     fortunes
    0.06
     inland
    0.06
    unched
    0.06
     extravagant
    0.06
     والت
    0.06
     мн
    0.06
    Act Density 0.061%

    No Known Activations