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

    Neuronpedia

    INDEX
    Explanations

    hockey

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    js
    -0.07
     Bottom
    -0.07
    Beam
    -0.07
     Barn
    -0.06
     DESCRIPTION
    -0.06
    �
    -0.06
     generals
    -0.06
    --------------------------------------------------------------------------↵
    -0.06
    资金
    -0.06
     위
    -0.06
    POSITIVE LOGITS
    Are
    0.07
     Dota
    0.06
     Ancient
    0.06
    Ich
    0.06
     deletes
    0.06
    SJ
    0.06
    ionic
    0.06
    -char
    0.06
     onu
    0.06
     depend
    0.06
    Act Density 0.001%

    No Known Activations