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

    Neuronpedia

    INDEX
    Explanations

    homes and rooms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Sexy
    -0.07
    alice
    -0.07
     (~(
    -0.07
    illions
    -0.06
    _exe
    -0.06
     Trần
    -0.06
    ível
    -0.06
    iado
    -0.06
    bler
    -0.06
    POSITIVE LOGITS
     Baghd
    0.07
     э
    0.06
     इन
    0.06
    (Y
    0.06
     Abort
    0.06
    兵
    0.06
     herramient
    0.06
    .HE
    0.06
     Rust
    0.06
     PY
    0.06
    Act Density 0.011%

    No Known Activations