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

    Neuronpedia

    INDEX
    Explanations

    poetry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coordinated
    -0.07
     domic
    -0.07
     explaining
    -0.06
     darling
    -0.06
     dic
    -0.06
    不堪
    -0.06
    blood
    -0.06
     Eric
    -0.06
     cleaner
    -0.06
     particle
    -0.06
    POSITIVE LOGITS
     "=
    0.08
     �
    0.07
    𬶋
    0.07
     Dol
    0.07
    漴
    0.07
    Sur
    0.07
     RTBU
    0.07
     FRONT
    0.07
    槛
    0.07
    渔
    0.07
    Act Density 0.085%

    No Known Activations