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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Equation
    -0.06
     whatsapp
    -0.06
    _secs
    -0.06
    μφωνα
    -0.06
     Gdk
    -0.06
     igual
    -0.06
    retain
    -0.06
    부
    -0.06
     enters
    -0.06
     zo
    -0.06
    POSITIVE LOGITS
    ")]
↵
    0.07
    �
    0.06
     fluorescent
    0.06
     slime
    0.06
    том
    0.06
    �
    0.06
    .synthetic
    0.06
    /avatar
    0.06
     smells
    0.06
    )]
    0.06
    Act Density 0.201%

    No Known Activations