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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     니
    -0.07
     denial
    -0.06
    eração
    -0.06
     nt
    -0.06
     Goldberg
    -0.06
     première
    -0.06
    še
    -0.06
    acro
    -0.06
    Reality
    -0.06
     Nuclear
    -0.06
    POSITIVE LOGITS
    ritable
    0.07
     *);↵
    0.07
    σουν
    0.07
     pocházet
    0.06
     उसक
    0.06
    ]?
    0.06
    Pear
    0.06
    0.06
    _link
    0.06
     Amendment
    0.06
    Act Density 0.000%

    No Known Activations