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

    Neuronpedia

    INDEX
    Explanations

    Alphanumeric strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Humans
    -0.07
    째
    -0.07
    ASTER
    -0.07
    �
    -0.06
    FLT
    -0.06
     dne
    -0.06
    "d
    -0.06
     obligatory
    -0.06
     ole
    -0.06
    ."/
    -0.06
    POSITIVE LOGITS
     Registro
    0.07
    ��
    0.07
     Geb
    0.07
     compounded
    0.06
    (al
    0.06
    urgy
    0.06
    ibli
    0.06
     scrambling
    0.06
     Dealers
    0.06
     magma
    0.06
    Act Density 0.008%

    No Known Activations