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

    Neuronpedia

    INDEX
    Explanations

    Facts and falsehoods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Recursive
    -0.07
    лении
    -0.06
     jih
    -0.06
    _regs
    -0.06
     врач
    -0.06
     errs
    -0.06
     LH
    -0.06
    .ForeignKey
    -0.06
     Kashmir
    -0.06
    爷
    -0.06
    POSITIVE LOGITS
    odynamic
    0.07
    annual
    0.07
    пня
    0.06
    595
    0.06
     additive
    0.06
     disk
    0.06
    liğinin
    0.06
     intra
    0.06
    妇
    0.06
    _CAN
    0.06
    Act Density 0.002%

    No Known Activations