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

    Neuronpedia

    INDEX
    Explanations

    objective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Storm
    -0.08
     Sterling
    -0.07
     Appointment
    -0.07
     Clarkson
    -0.07
     сотруд
    -0.07
     renegot
    -0.06
    Coal
    -0.06
    Ask
    -0.06
    overnment
    -0.06
     Potato
    -0.06
    POSITIVE LOGITS
     годы
    0.08
    ทรา
    0.08
    trägt
    0.07
    以上の
    0.07
     يجعل
    0.07
     חושב
    0.07
     }];↵↵
    0.07
    ewed
    0.07
    利于
    0.07
     لأ
    0.07
    Act Density 0.041%

    No Known Activations