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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /Object
    -0.07
    :{↵
    -0.07
     Format
    -0.06
    /bl
    -0.06
     horizontal
    -0.06
     Database
    -0.06
    22
    -0.06
     Modifier
    -0.06
    Enabled
    -0.06
     magnitude
    -0.06
    POSITIVE LOGITS
    �
    0.07
    ...↵↵↵
    0.07
    áte
    0.06
    -set
    0.06
    (real
    0.06
    Ao
    0.06
    (super
    0.06
    (nb
    0.06
    Below
    0.06
    /Observable
    0.06
    Act Density 0.083%

    No Known Activations