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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     か
    -0.07
    HEMA
    -0.07
    _bytes
    -0.06
    Movie
    -0.06
    PAR
    -0.06
    roma
    -0.06
     Велик
    -0.06
     neutron
    -0.06
    _components
    -0.06
    asons
    -0.06
    POSITIVE LOGITS
    .skill
    0.07
     samsung
    0.07
    :[],↵
    0.07
    -alt
    0.07
    .FALSE
    0.06
    ำ
    0.06
    ("'",
    0.06
     đức
    0.06
     STDMETHOD
    0.06
    iesel
    0.06
    Act Density 0.006%

    No Known Activations