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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ังหว
    -0.06
    -0.06
     Bloc
    -0.06
     fiction
    -0.06
    TabIndex
    -0.06
     nu
    -0.06
    old
    -0.06
    ":"",↵
    -0.06
     вч
    -0.05
    APO
    -0.05
    POSITIVE LOGITS
     HS
    0.07
     контролю
    0.07
    artic
    0.07
    ínu
    0.07
    �
    0.06
    .private
    0.06
    مش
    0.06
    掛
    0.06
     Herman
    0.06
    agency
    0.06
    Act Density 0.051%

    No Known Activations