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

    Neuronpedia

    INDEX
    Explanations

    be/have verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    рак
    -0.07
    	height
    -0.07
    _proj
    -0.06
    approved
    -0.06
    ,),
    -0.06
    Notifications
    -0.06
     сум
    -0.06
     sequences
    -0.06
     подв
    -0.06
    InOut
    -0.06
    POSITIVE LOGITS
    "text
    0.08
    Î
    0.07
    _song
    0.07
     poměr
    0.06
    /content
    0.06
    �
    0.06
    ";"
    0.06
     Iz
    0.06
    絶
    0.06
    .setOutput
    0.06
    Act Density 0.132%

    No Known Activations