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

    Neuronpedia

    INDEX
    Explanations

    ++)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SIDE
    -0.07
     sanitizer
    -0.07
    Annotations
    -0.06
    .She
    -0.06
    CONTEXT
    -0.06
     ImportError
    -0.06
    (Matrix
    -0.06
     Salt
    -0.06
     defenses
    -0.05
     dignity
    -0.05
    POSITIVE LOGITS
    у
    0.07
    óst
    0.07
    indi
    0.07
     корм
    0.07
    \Queue
    0.07
    ymph
    0.06
     Couples
    0.06
     Quarter
    0.06
     Mant
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations