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

    Neuronpedia

    INDEX
    Explanations

    Jalapeno peppers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hyper
    -0.07
    _TRNS
    -0.07
    biology
    -0.06
    index
    -0.06
     schedules
    -0.06
     imm
    -0.06
     theorem
    -0.06
    Via
    -0.06
     uniqueness
    -0.06
     parallels
    -0.06
    POSITIVE LOGITS
    ��
    0.07
     bö
    0.07
    шир
    0.07
    км
    0.06
    _TLS
    0.06
     сопров
    0.06
    ););↵
    0.06
    ++++++++++++++++++++++++++++++++
    0.06
     Loki
    0.06
    azer
    0.06
    Act Density 0.001%

    No Known Activations