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

    Neuronpedia

    INDEX
    Explanations

    ms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Err
    -0.08
    彰
    -0.08
     wäre
    -0.07
     thunk
    -0.07
    珩
    -0.07
    탙
    -0.07
     Schro
    -0.07
    anches
    -0.07
    钏
    -0.07
    着实
    -0.07
    POSITIVE LOGITS
    /J
    0.08
     objetos
    0.08
    泥土
    0.08
    [string
    0.08
    油漆
    0.07
     anatom
    0.07
     jewel
    0.07
    atomy
    0.07
    wizard
    0.07
    gm
    0.07
    Act Density 0.001%

    No Known Activations