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

    Neuronpedia

    INDEX
    Explanations

    Auxiliary Verbs of Requirement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buk
    -0.06
    phis
    -0.06
    ；↵
    -0.06
     Kirk
    -0.06
     unloaded
    -0.06
    steps
    -0.06
     })
↵
    -0.06
    909
    -0.06
     Bieber
    -0.06
     Vertical
    -0.06
    POSITIVE LOGITS
     默认
    0.07
     constraints
    0.07
     smiles
    0.07
    .routes
    0.07
    uffix
    0.07
     constraint
    0.06
    -mode
    0.06
     ignite
    0.06
    weights
    0.06
     tant
    0.06
    Act Density 0.006%

    No Known Activations