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

    Neuronpedia

    INDEX
    Explanations

    code file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    لاح
    -0.07
     Though
    -0.07
    208
    -0.06
    .getView
    -0.06
     investigators
    -0.06
     bridge
    -0.06
     headed
    -0.06
     unlocked
    -0.06
     PDF
    -0.06
    Congratulations
    -0.06
    POSITIVE LOGITS
     куп
    0.06
     NXT
    0.06
    bral
    0.06
    빈
    0.06
    ileen
    0.06
    oen
    0.06
    ाइक
    0.06
    �
    0.06
    ibble
    0.06
    feeding
    0.06
    Act Density 0.009%

    No Known Activations