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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attendance
    -0.07
    ید
    -0.06
    Decl
    -0.06
    (scan
    -0.06
    (xy
    -0.06
    .mass
    -0.06
     interstate
    -0.06
     backs
    -0.06
    ід
    -0.06
    STM
    -0.06
    POSITIVE LOGITS
    Carol
    0.08
    Prec
    0.07
     газ
    0.07
     druhou
    0.06
    /REC
    0.06
    	resolve
    0.06
    ادگی
    0.06
     Hair
    0.06
     violating
    0.06
     Thai
    0.06
    Act Density 0.000%

    No Known Activations