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

    Neuronpedia

    INDEX
    Explanations

    hosts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ngh
    -0.07
    PLAY
    -0.06
     frente
    -0.06
     rugged
    -0.06
    Nota
    -0.06
     love
    -0.06
    tml
    -0.06
     trough
    -0.06
     EVEN
    -0.06
    Record
    -0.06
    POSITIVE LOGITS
    isLoggedIn
    0.07
    737
    0.06
    )]
    0.06
     Jim
    0.06
    }$
    0.06
    }\\
    0.06
     독
    0.06
    )<
    0.06
     p
    0.06
     müşteri
    0.06
    Act Density 0.000%

    No Known Activations