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

    Neuronpedia

    INDEX
    Explanations

    NAME

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     digestive
    -0.07
    uC
    -0.07
     });
    -0.07
    २०
    -0.07
     �
    -0.07
     الات
    -0.07
    otta
    -0.07
    _SECURITY
    -0.07
    exus
    -0.07
    :`
    -0.07
    POSITIVE LOGITS
     name
    0.27
     NAME
    0.23
     Name
    0.22
    Name
    0.19
    name
    0.19
     names
    0.16
    (name
    0.16
    _name
    0.15
    NAME
    0.15
    -name
    0.15
    Act Density 0.417%

    No Known Activations