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

    Neuronpedia

    INDEX
    Explanations

    aure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мех
    -0.07
     Firebase
    -0.07
    egend
    -0.06
    _Login
    -0.06
    .М
    -0.06
    른
    -0.06
    	close
    -0.06
    JNI
    -0.06
    equ
    -0.06
    UTE
    -0.06
    POSITIVE LOGITS
    (phone
    0.06
     funkc
    0.06
    -rating
    0.06
    alloween
    0.06
    bakan
    0.06
     Іван
    0.06
     vows
    0.06
     preventing
    0.06
     господар
    0.06
     Clara
    0.06
    Act Density 0.007%

    No Known Activations