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

    Neuronpedia

    INDEX
    Explanations

    Ends/Ending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Characteristics
    -0.09
    Magnitude
    -0.09
    <java
    -0.08
     Cros
    -0.08
    Operands
    -0.08
     magnitude
    -0.08
     selbstverständlich
    -0.08
    .design
    -0.08
    Sides
    -0.07
     ثلاث
    -0.07
    POSITIVE LOGITS
     poign
    0.09
     bitters
    0.09
     hopeful
    0.09
     कविता
    0.08
     कथा
    0.08
     चिं
    0.08
     goodbye
    0.08
    ksa
    0.08
    暮
    0.08
     nostalgic
    0.08
    Act Density 0.022%

    No Known Activations